Update app.py

app.py

@@ -1,33 +1,51 @@
-import streamlit as st
+import gradio as gr
 import azure.cognitiveservices.speech as speechsdk
 
-# Azure Speech Service credentials
-speech_key = "12afe22c558a4f8d8bd28d6a67cdb9b0"
-service_region = "westus"
-
-def transcribe_audio(file_path):
+def assess_pronunciation(audio_file):
+    # Configure Azure Speech Service
+    speech_key = "YourAzureSpeechServiceKey"
+    service_region = "YourServiceRegion"
     speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
-    audio_input = speechsdk.AudioConfig(filename=file_path)
-    speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_input)
+    
+    # Set up the audio configuration
+    audio_config = speechsdk.audio.AudioConfig(filename=audio_file)
+    
+    # Create pronunciation assessment config
+    pronunciation_config = speechsdk.PronunciationAssessmentConfig(
+        reference_text="你好",
+        grading_system=speechsdk.PronunciationAssessmentGradingSystem.HundredMark,
+        granularity=speechsdk.PronunciationAssessmentGranularity.Phoneme
+    )
+    pronunciation_config.enable_prosody_assessment()
 
-    result = speech_recognizer.recognize_once()
-    if result.reason == speechsdk.ResultReason.RecognizedSpeech:
-        return result.text
-    elif result.reason == speechsdk.ResultReason.NoMatch:
-        return "No speech could be recognized"
-    else:
-        return "Speech recognition canceled: {}".format(result.cancellation_details.reason)
+    # Create the recognizer
+    recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
+    pronunciation_config.apply_to(recognizer)
 
-st.title("Chinese Pronunciation Checker")
+    # Recognize speech and assess pronunciation
+    result = recognizer.recognize_once()
+    pronunciation_result = speechsdk.PronunciationAssessmentResult(result)
+    
+    # Extract and format the results
+    accuracy_score = pronunciation_result.accuracy_score
+    fluency_score = pronunciation_result.fluency_score
+    completeness_score = pronunciation_result.completeness_score
+    prosody_score = pronunciation_result.prosody_score
 
-uploaded_file = st.file_uploader("Choose an audio file", type=["wav", "mp3"])
+    return {
+        "Accuracy": accuracy_score,
+        "Fluency": fluency_score,
+        "Completeness": completeness_score,
+        "Prosody": prosody_score
+    }
 
-if uploaded_file is not None:
-    st.audio(uploaded_file, format="audio/wav")
-    file_path = f"temp_audio.{uploaded_file.type.split('/')[-1]}"
-    
-    with open(file_path, "wb") as f:
-        f.write(uploaded_file.getbuffer())
+# Create Gradio interface
+interface = gr.Interface(
+    fn=assess_pronunciation,
+    inputs=gr.Audio(source="upload", type="filepath"),
+    outputs="json",
+    title="Chinese Pronunciation Checker"
+)
 
-    transcript = transcribe_audio(file_path)
-    st.write("Transcribed Text: ", transcript)
+if __name__ == "__main__":
+    interface.launch()